Citation

Ma X, Dai Z, He Z, Ma J, Wang Y, Wang Y. Sensors (Basel) 2017; 17(4): s17040818.

Affiliation

School of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control, Beihang University, Beijing 100191, China. ypwang@buaa.edu.cn.

Copyright

(Copyright © 2017, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s17040818

PMID

28394270

Abstract

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Language: en

Keywords

convolutional neural network; deep learning; spatiotemporal feature; traffic speed prediction; transportation network